#include <linux/blkdev.h>
#include <linux/kthread.h>
+#include <linux/raid/pq.h>
#include <linux/async_tx.h>
#include <linux/seq_file.h>
#include "md.h"
#include "raid5.h"
-#include "raid6.h"
#include "bitmap.h"
/*
#define printk_rl(args...) ((void) (printk_ratelimit() && printk(args)))
-#if !RAID6_USE_EMPTY_ZERO_PAGE
-/* In .bss so it's zeroed */
-const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
-#endif
-
/*
* We maintain a biased count of active stripes in the bottom 16 bits of
* bi_phys_segments, and a count of processed stripes in the upper 16 bits
return 0;
}
-static void raid5_build_block(struct stripe_head *sh, int i);
+static void raid5_build_block(struct stripe_head *sh, int i, int previous);
static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
struct stripe_head *sh);
remove_hash(sh);
+ sh->generation = conf->generation - previous;
sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks;
sh->sector = sector;
stripe_set_idx(sector, conf, previous, sh);
BUG();
}
dev->flags = 0;
- raid5_build_block(sh, i);
+ raid5_build_block(sh, i, previous);
}
insert_hash(conf, sh);
}
-static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, int disks)
+static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector,
+ short generation)
{
struct stripe_head *sh;
struct hlist_node *hn;
CHECK_DEVLOCK();
pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector);
hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
- if (sh->sector == sector && sh->disks == disks)
+ if (sh->sector == sector && sh->generation == generation)
return sh;
pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector);
return NULL;
int previous, int noblock)
{
struct stripe_head *sh;
- int disks = previous ? conf->previous_raid_disks : conf->raid_disks;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
wait_event_lock_irq(conf->wait_for_stripe,
conf->quiesce == 0,
conf->device_lock, /* nothing */);
- sh = __find_stripe(conf, sector, disks);
+ sh = __find_stripe(conf, sector, conf->generation - previous);
if (!sh) {
if (!conf->inactive_blocked)
sh = get_free_stripe(conf);
init_stripe(sh, sector, previous);
} else {
if (atomic_read(&sh->count)) {
- BUG_ON(!list_empty(&sh->lru));
+ BUG_ON(!list_empty(&sh->lru)
+ && !test_bit(STRIPE_EXPANDING, &sh->state));
} else {
if (!test_bit(STRIPE_HANDLE, &sh->state))
atomic_inc(&conf->active_stripes);
return 0;
}
-#ifdef CONFIG_MD_RAID5_RESHAPE
static int resize_stripes(raid5_conf_t *conf, int newsize)
{
/* Make all the stripes able to hold 'newsize' devices.
conf->pool_size = newsize;
return err;
}
-#endif
static int drop_one_stripe(raid5_conf_t *conf)
{
}
-static sector_t compute_blocknr(struct stripe_head *sh, int i);
+static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous);
-static void raid5_build_block(struct stripe_head *sh, int i)
+static void raid5_build_block(struct stripe_head *sh, int i, int previous)
{
struct r5dev *dev = &sh->dev[i];
dev->req.bi_private = sh;
dev->flags = 0;
- dev->sector = compute_blocknr(sh, i);
+ dev->sector = compute_blocknr(sh, i, previous);
}
static void error(mddev_t *mddev, mdk_rdev_t *rdev)
int pd_idx, qd_idx;
int ddf_layout = 0;
sector_t new_sector;
- int sectors_per_chunk = conf->chunk_size >> 9;
+ int algorithm = previous ? conf->prev_algo
+ : conf->algorithm;
+ int sectors_per_chunk = previous ? (conf->prev_chunk >> 9)
+ : (conf->chunk_size >> 9);
int raid_disks = previous ? conf->previous_raid_disks
: conf->raid_disks;
int data_disks = raid_disks - conf->max_degraded;
pd_idx = data_disks;
break;
case 5:
- switch (conf->algorithm) {
+ switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
pd_idx = data_disks - stripe % raid_disks;
if (*dd_idx >= pd_idx)
break;
default:
printk(KERN_ERR "raid5: unsupported algorithm %d\n",
- conf->algorithm);
+ algorithm);
BUG();
}
break;
case 6:
- switch (conf->algorithm) {
+ switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
pd_idx = raid_disks - 1 - (stripe % raid_disks);
qd_idx = pd_idx + 1;
default:
printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
- conf->algorithm);
+ algorithm);
BUG();
}
break;
}
-static sector_t compute_blocknr(struct stripe_head *sh, int i)
+static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
{
raid5_conf_t *conf = sh->raid_conf;
int raid_disks = sh->disks;
int data_disks = raid_disks - conf->max_degraded;
sector_t new_sector = sh->sector, check;
- int sectors_per_chunk = conf->chunk_size >> 9;
+ int sectors_per_chunk = previous ? (conf->prev_chunk >> 9)
+ : (conf->chunk_size >> 9);
+ int algorithm = previous ? conf->prev_algo
+ : conf->algorithm;
sector_t stripe;
int chunk_offset;
int chunk_number, dummy1, dd_idx = i;
switch(conf->level) {
case 4: break;
case 5:
- switch (conf->algorithm) {
+ switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
case ALGORITHM_RIGHT_ASYMMETRIC:
if (i > sh->pd_idx)
break;
default:
printk(KERN_ERR "raid5: unsupported algorithm %d\n",
- conf->algorithm);
+ algorithm);
BUG();
}
break;
case 6:
if (i == sh->qd_idx)
return 0; /* It is the Q disk */
- switch (conf->algorithm) {
+ switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
case ALGORITHM_RIGHT_ASYMMETRIC:
case ALGORITHM_ROTATING_ZERO_RESTART:
break;
default:
printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
- conf->algorithm);
+ algorithm);
BUG();
}
break;
r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset;
check = raid5_compute_sector(conf, r_sector,
- (raid_disks != conf->raid_disks),
- &dummy1, &sh2);
+ previous, &dummy1, &sh2);
if (check != sh->sector || dummy1 != dd_idx || sh2.pd_idx != sh->pd_idx
|| sh2.qd_idx != sh->qd_idx) {
printk(KERN_ERR "compute_blocknr: map not correct\n");
static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
struct stripe_head *sh)
{
- int sectors_per_chunk = conf->chunk_size >> 9;
+ int sectors_per_chunk =
+ previous ? (conf->prev_chunk >> 9)
+ : (conf->chunk_size >> 9);
int dd_idx;
int chunk_offset = sector_div(stripe, sectors_per_chunk);
int disks = previous ? conf->previous_raid_disks : conf->raid_disks;
struct r6_state *r6s, int disks)
{
int rcw = 0, must_compute = 0, pd_idx = sh->pd_idx, i;
- int qd_idx = r6s->qd_idx;
+ int qd_idx = sh->qd_idx;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
/* Would I have to read this buffer for reconstruct_write */
int update_p = 0, update_q = 0;
struct r5dev *dev;
int pd_idx = sh->pd_idx;
- int qd_idx = r6s->qd_idx;
+ int qd_idx = sh->qd_idx;
set_bit(STRIPE_HANDLE, &sh->state);
struct dma_async_tx_descriptor *tx = NULL;
clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
for (i = 0; i < sh->disks; i++)
- if (i != sh->pd_idx && (!r6s || i != r6s->qd_idx)) {
+ if (i != sh->pd_idx && i != sh->qd_idx) {
int dd_idx, j;
struct stripe_head *sh2;
- sector_t bn = compute_blocknr(sh, i);
+ sector_t bn = compute_blocknr(sh, i, 1);
sector_t s = raid5_compute_sector(conf, bn, 0,
&dd_idx, NULL);
sh2 = get_active_stripe(conf, s, 0, 1);
/* Finish reconstruct operations initiated by the expansion process */
if (sh->reconstruct_state == reconstruct_state_result) {
+ struct stripe_head *sh2
+ = get_active_stripe(conf, sh->sector, 1, 1);
+ if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
+ /* sh cannot be written until sh2 has been read.
+ * so arrange for sh to be delayed a little
+ */
+ set_bit(STRIPE_DELAYED, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
+ &sh2->state))
+ atomic_inc(&conf->preread_active_stripes);
+ release_stripe(sh2);
+ goto unlock;
+ }
+ if (sh2)
+ release_stripe(sh2);
+
sh->reconstruct_state = reconstruct_state_idle;
clear_bit(STRIPE_EXPANDING, &sh->state);
for (i = conf->raid_disks; i--; ) {
raid5_conf_t *conf = sh->raid_conf;
int disks = sh->disks;
struct bio *return_bi = NULL;
- int i, pd_idx = sh->pd_idx;
+ int i, pd_idx = sh->pd_idx, qd_idx = sh->qd_idx;
struct stripe_head_state s;
struct r6_state r6s;
struct r5dev *dev, *pdev, *qdev;
mdk_rdev_t *blocked_rdev = NULL;
- r6s.qd_idx = sh->qd_idx;
pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
"pd_idx=%d, qd_idx=%d\n",
(unsigned long long)sh->sector, sh->state,
- atomic_read(&sh->count), pd_idx, r6s.qd_idx);
+ atomic_read(&sh->count), pd_idx, qd_idx);
memset(&s, 0, sizeof(s));
spin_lock(&sh->lock);
pdev = &sh->dev[pd_idx];
r6s.p_failed = (s.failed >= 1 && r6s.failed_num[0] == pd_idx)
|| (s.failed >= 2 && r6s.failed_num[1] == pd_idx);
- qdev = &sh->dev[r6s.qd_idx];
- r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == r6s.qd_idx)
- || (s.failed >= 2 && r6s.failed_num[1] == r6s.qd_idx);
+ qdev = &sh->dev[qd_idx];
+ r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == qd_idx)
+ || (s.failed >= 2 && r6s.failed_num[1] == qd_idx);
if ( s.written &&
( r6s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
}
if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
+ struct stripe_head *sh2
+ = get_active_stripe(conf, sh->sector, 1, 1);
+ if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
+ /* sh cannot be written until sh2 has been read.
+ * so arrange for sh to be delayed a little
+ */
+ set_bit(STRIPE_DELAYED, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
+ &sh2->state))
+ atomic_inc(&conf->preread_active_stripes);
+ release_stripe(sh2);
+ goto unlock;
+ }
+ if (sh2)
+ release_stripe(sh2);
+
/* Need to write out all blocks after computing P&Q */
sh->disks = conf->raid_disks;
stripe_set_idx(sh->sector, conf, 0, sh);
if ((bvm->bi_rw & 1) == WRITE)
return biovec->bv_len; /* always allow writes to be mergeable */
+ if (mddev->new_chunk < mddev->chunk_size)
+ chunk_sectors = mddev->new_chunk >> 9;
max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
if (max < 0) max = 0;
if (max <= biovec->bv_len && bio_sectors == 0)
unsigned int chunk_sectors = mddev->chunk_size >> 9;
unsigned int bio_sectors = bio->bi_size >> 9;
+ if (mddev->new_chunk < mddev->chunk_size)
+ chunk_sectors = mddev->new_chunk >> 9;
return chunk_sectors >=
((sector & (chunk_sectors - 1)) + bio_sectors);
}
retry:
previous = 0;
+ disks = conf->raid_disks;
prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
- if (likely(conf->expand_progress == MaxSector))
- disks = conf->raid_disks;
- else {
- /* spinlock is needed as expand_progress may be
+ if (unlikely(conf->reshape_progress != MaxSector)) {
+ /* spinlock is needed as reshape_progress may be
* 64bit on a 32bit platform, and so it might be
* possible to see a half-updated value
- * Ofcourse expand_progress could change after
+ * Ofcourse reshape_progress could change after
* the lock is dropped, so once we get a reference
* to the stripe that we think it is, we will have
* to check again.
*/
spin_lock_irq(&conf->device_lock);
- disks = conf->raid_disks;
- if (logical_sector >= conf->expand_progress) {
+ if (mddev->delta_disks < 0
+ ? logical_sector < conf->reshape_progress
+ : logical_sector >= conf->reshape_progress) {
disks = conf->previous_raid_disks;
previous = 1;
} else {
- if (logical_sector >= conf->expand_lo) {
+ if (mddev->delta_disks < 0
+ ? logical_sector < conf->reshape_safe
+ : logical_sector >= conf->reshape_safe) {
spin_unlock_irq(&conf->device_lock);
schedule();
goto retry;
sh = get_active_stripe(conf, new_sector, previous,
(bi->bi_rw&RWA_MASK));
if (sh) {
- if (unlikely(conf->expand_progress != MaxSector)) {
+ if (unlikely(previous)) {
/* expansion might have moved on while waiting for a
* stripe, so we must do the range check again.
* Expansion could still move past after this
*/
int must_retry = 0;
spin_lock_irq(&conf->device_lock);
- if (logical_sector < conf->expand_progress &&
- disks == conf->previous_raid_disks)
+ if (mddev->delta_disks < 0
+ ? logical_sector >= conf->reshape_progress
+ : logical_sector < conf->reshape_progress)
/* mismatch, need to try again */
must_retry = 1;
spin_unlock_irq(&conf->device_lock);
return 0;
}
+static sector_t raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks);
+
static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped)
{
/* reshaping is quite different to recovery/resync so it is
int new_data_disks = conf->raid_disks - conf->max_degraded;
int i;
int dd_idx;
- sector_t writepos, safepos, gap;
-
- if (sector_nr == 0 &&
- conf->expand_progress != 0) {
- /* restarting in the middle, skip the initial sectors */
- sector_nr = conf->expand_progress;
+ sector_t writepos, readpos, safepos;
+ sector_t stripe_addr;
+ int reshape_sectors;
+ struct list_head stripes;
+
+ if (sector_nr == 0) {
+ /* If restarting in the middle, skip the initial sectors */
+ if (mddev->delta_disks < 0 &&
+ conf->reshape_progress < raid5_size(mddev, 0, 0)) {
+ sector_nr = raid5_size(mddev, 0, 0)
+ - conf->reshape_progress;
+ } else if (mddev->delta_disks > 0 &&
+ conf->reshape_progress > 0)
+ sector_nr = conf->reshape_progress;
sector_div(sector_nr, new_data_disks);
- *skipped = 1;
- return sector_nr;
+ if (sector_nr) {
+ *skipped = 1;
+ return sector_nr;
+ }
}
+ /* We need to process a full chunk at a time.
+ * If old and new chunk sizes differ, we need to process the
+ * largest of these
+ */
+ if (mddev->new_chunk > mddev->chunk_size)
+ reshape_sectors = mddev->new_chunk / 512;
+ else
+ reshape_sectors = mddev->chunk_size / 512;
+
/* we update the metadata when there is more than 3Meg
* in the block range (that is rather arbitrary, should
* probably be time based) or when the data about to be
* copied would over-write the source of the data at
* the front of the range.
- * i.e. one new_stripe forward from expand_progress new_maps
- * to after where expand_lo old_maps to
+ * i.e. one new_stripe along from reshape_progress new_maps
+ * to after where reshape_safe old_maps to
*/
- writepos = conf->expand_progress +
- conf->chunk_size/512*(new_data_disks);
+ writepos = conf->reshape_progress;
sector_div(writepos, new_data_disks);
- safepos = conf->expand_lo;
+ readpos = conf->reshape_progress;
+ sector_div(readpos, data_disks);
+ safepos = conf->reshape_safe;
sector_div(safepos, data_disks);
- gap = conf->expand_progress - conf->expand_lo;
+ if (mddev->delta_disks < 0) {
+ writepos -= min_t(sector_t, reshape_sectors, writepos);
+ readpos += reshape_sectors;
+ safepos += reshape_sectors;
+ } else {
+ writepos += reshape_sectors;
+ readpos -= min_t(sector_t, reshape_sectors, readpos);
+ safepos -= min_t(sector_t, reshape_sectors, safepos);
+ }
- if (writepos >= safepos ||
- gap > (new_data_disks)*3000*2 /*3Meg*/) {
+ /* 'writepos' is the most advanced device address we might write.
+ * 'readpos' is the least advanced device address we might read.
+ * 'safepos' is the least address recorded in the metadata as having
+ * been reshaped.
+ * If 'readpos' is behind 'writepos', then there is no way that we can
+ * ensure safety in the face of a crash - that must be done by userspace
+ * making a backup of the data. So in that case there is no particular
+ * rush to update metadata.
+ * Otherwise if 'safepos' is behind 'writepos', then we really need to
+ * update the metadata to advance 'safepos' to match 'readpos' so that
+ * we can be safe in the event of a crash.
+ * So we insist on updating metadata if safepos is behind writepos and
+ * readpos is beyond writepos.
+ * In any case, update the metadata every 10 seconds.
+ * Maybe that number should be configurable, but I'm not sure it is
+ * worth it.... maybe it could be a multiple of safemode_delay???
+ */
+ if ((mddev->delta_disks < 0
+ ? (safepos > writepos && readpos < writepos)
+ : (safepos < writepos && readpos > writepos)) ||
+ time_after(jiffies, conf->reshape_checkpoint + 10*HZ)) {
/* Cannot proceed until we've updated the superblock... */
wait_event(conf->wait_for_overlap,
atomic_read(&conf->reshape_stripes)==0);
- mddev->reshape_position = conf->expand_progress;
+ mddev->reshape_position = conf->reshape_progress;
+ mddev->curr_resync_completed = mddev->curr_resync;
+ conf->reshape_checkpoint = jiffies;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
md_wakeup_thread(mddev->thread);
wait_event(mddev->sb_wait, mddev->flags == 0 ||
kthread_should_stop());
spin_lock_irq(&conf->device_lock);
- conf->expand_lo = mddev->reshape_position;
+ conf->reshape_safe = mddev->reshape_position;
spin_unlock_irq(&conf->device_lock);
wake_up(&conf->wait_for_overlap);
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
- for (i=0; i < conf->chunk_size/512; i+= STRIPE_SECTORS) {
+ if (mddev->delta_disks < 0) {
+ BUG_ON(conf->reshape_progress == 0);
+ stripe_addr = writepos;
+ BUG_ON((mddev->dev_sectors &
+ ~((sector_t)reshape_sectors - 1))
+ - reshape_sectors - stripe_addr
+ != sector_nr);
+ } else {
+ BUG_ON(writepos != sector_nr + reshape_sectors);
+ stripe_addr = sector_nr;
+ }
+ INIT_LIST_HEAD(&stripes);
+ for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
int j;
int skipped = 0;
- sh = get_active_stripe(conf, sector_nr+i, 0, 0);
+ sh = get_active_stripe(conf, stripe_addr+i, 0, 0);
set_bit(STRIPE_EXPANDING, &sh->state);
atomic_inc(&conf->reshape_stripes);
/* If any of this stripe is beyond the end of the old
if (conf->level == 6 &&
j == sh->qd_idx)
continue;
- s = compute_blocknr(sh, j);
- if (s < mddev->array_sectors) {
+ s = compute_blocknr(sh, j, 0);
+ if (s < raid5_size(mddev, 0, 0)) {
skipped = 1;
continue;
}
set_bit(STRIPE_EXPAND_READY, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
}
- release_stripe(sh);
+ list_add(&sh->lru, &stripes);
}
spin_lock_irq(&conf->device_lock);
- conf->expand_progress = (sector_nr + i) * new_data_disks;
+ if (mddev->delta_disks < 0)
+ conf->reshape_progress -= reshape_sectors * new_data_disks;
+ else
+ conf->reshape_progress += reshape_sectors * new_data_disks;
spin_unlock_irq(&conf->device_lock);
/* Ok, those stripe are ready. We can start scheduling
* reads on the source stripes.
* block on the destination stripes.
*/
first_sector =
- raid5_compute_sector(conf, sector_nr*(new_data_disks),
+ raid5_compute_sector(conf, stripe_addr*(new_data_disks),
1, &dd_idx, NULL);
last_sector =
- raid5_compute_sector(conf, ((sector_nr+conf->chunk_size/512)
+ raid5_compute_sector(conf, ((stripe_addr+conf->chunk_size/512)
*(new_data_disks) - 1),
1, &dd_idx, NULL);
if (last_sector >= mddev->dev_sectors)
release_stripe(sh);
first_sector += STRIPE_SECTORS;
}
+ /* Now that the sources are clearly marked, we can release
+ * the destination stripes
+ */
+ while (!list_empty(&stripes)) {
+ sh = list_entry(stripes.next, struct stripe_head, lru);
+ list_del_init(&sh->lru);
+ release_stripe(sh);
+ }
/* If this takes us to the resync_max point where we have to pause,
* then we need to write out the superblock.
*/
- sector_nr += conf->chunk_size>>9;
- if (sector_nr >= mddev->resync_max) {
+ sector_nr += reshape_sectors;
+ if ((sector_nr - mddev->curr_resync_completed) * 2
+ >= mddev->resync_max - mddev->curr_resync_completed) {
/* Cannot proceed until we've updated the superblock... */
wait_event(conf->wait_for_overlap,
atomic_read(&conf->reshape_stripes) == 0);
- mddev->reshape_position = conf->expand_progress;
+ mddev->reshape_position = conf->reshape_progress;
+ mddev->curr_resync_completed = mddev->curr_resync;
+ conf->reshape_checkpoint = jiffies;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
md_wakeup_thread(mddev->thread);
wait_event(mddev->sb_wait,
!test_bit(MD_CHANGE_DEVS, &mddev->flags)
|| kthread_should_stop());
spin_lock_irq(&conf->device_lock);
- conf->expand_lo = mddev->reshape_position;
+ conf->reshape_safe = mddev->reshape_position;
spin_unlock_irq(&conf->device_lock);
wake_up(&conf->wait_for_overlap);
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
- return conf->chunk_size>>9;
+ return reshape_sectors;
}
/* FIXME go_faster isn't used */
if (sector_nr >= max_sector) {
/* just being told to finish up .. nothing much to do */
unplug_slaves(mddev);
+
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
end_reshape(conf);
return 0;
.attrs = raid5_attrs,
};
+static sector_t
+raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+
+ if (!sectors)
+ sectors = mddev->dev_sectors;
+ if (!raid_disks) {
+ /* size is defined by the smallest of previous and new size */
+ if (conf->raid_disks < conf->previous_raid_disks)
+ raid_disks = conf->raid_disks;
+ else
+ raid_disks = conf->previous_raid_disks;
+ }
+
+ sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
+ sectors &= ~((sector_t)mddev->new_chunk/512 - 1);
+ return sectors * (raid_disks - conf->max_degraded);
+}
+
static raid5_conf_t *setup_conf(mddev_t *mddev)
{
raid5_conf_t *conf;
conf->max_degraded = 1;
conf->algorithm = mddev->new_layout;
conf->max_nr_stripes = NR_STRIPES;
- conf->expand_progress = mddev->reshape_position;
+ conf->reshape_progress = mddev->reshape_position;
+ if (conf->reshape_progress != MaxSector) {
+ conf->prev_chunk = mddev->chunk_size;
+ conf->prev_algo = mddev->layout;
+ }
memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
conf->raid_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
*/
sector_t here_new, here_old;
int old_disks;
- int max_degraded = (mddev->level == 5 ? 1 : 2);
+ int max_degraded = (mddev->level == 6 ? 2 : 1);
- if (mddev->new_level != mddev->level ||
- mddev->new_layout != mddev->layout ||
- mddev->new_chunk != mddev->chunk_size) {
+ if (mddev->new_level != mddev->level) {
printk(KERN_ERR "raid5: %s: unsupported reshape "
"required - aborting.\n",
mdname(mddev));
return -EINVAL;
}
- if (mddev->delta_disks <= 0) {
- printk(KERN_ERR "raid5: %s: unsupported reshape "
- "(reduce disks) required - aborting.\n",
- mdname(mddev));
- return -EINVAL;
- }
old_disks = mddev->raid_disks - mddev->delta_disks;
/* reshape_position must be on a new-stripe boundary, and one
* further up in new geometry must map after here in old
* geometry.
*/
here_new = mddev->reshape_position;
- if (sector_div(here_new, (mddev->chunk_size>>9)*
+ if (sector_div(here_new, (mddev->new_chunk>>9)*
(mddev->raid_disks - max_degraded))) {
printk(KERN_ERR "raid5: reshape_position not "
"on a stripe boundary\n");
if (mddev->degraded == 0)
printk("raid5: raid level %d set %s active with %d out of %d"
- " devices, algorithm %d\n", conf->level, mdname(mddev),
- mddev->raid_disks-mddev->degraded, mddev->raid_disks,
- conf->algorithm);
+ " devices, algorithm %d\n", conf->level, mdname(mddev),
+ mddev->raid_disks-mddev->degraded, mddev->raid_disks,
+ mddev->new_layout);
else
printk(KERN_ALERT "raid5: raid level %d set %s active with %d"
" out of %d devices, algorithm %d\n", conf->level,
mdname(mddev), mddev->raid_disks - mddev->degraded,
- mddev->raid_disks, conf->algorithm);
+ mddev->raid_disks, mddev->new_layout);
print_raid5_conf(conf);
- if (conf->expand_progress != MaxSector) {
+ if (conf->reshape_progress != MaxSector) {
printk("...ok start reshape thread\n");
- conf->expand_lo = conf->expand_progress;
+ conf->reshape_safe = conf->reshape_progress;
atomic_set(&conf->reshape_stripes, 0);
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
mddev->queue->backing_dev_info.congested_data = mddev;
mddev->queue->backing_dev_info.congested_fn = raid5_congested;
- mddev->array_sectors = mddev->dev_sectors *
- (conf->previous_raid_disks - conf->max_degraded);
+ md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
print_raid5_conf(conf);
rdev = p->rdev;
if (rdev) {
+ if (number >= conf->raid_disks &&
+ conf->reshape_progress == MaxSector)
+ clear_bit(In_sync, &rdev->flags);
+
if (test_bit(In_sync, &rdev->flags) ||
atomic_read(&rdev->nr_pending)) {
err = -EBUSY;
* isn't possible.
*/
if (!test_bit(Faulty, &rdev->flags) &&
- mddev->degraded <= conf->max_degraded) {
+ mddev->degraded <= conf->max_degraded &&
+ number < conf->raid_disks) {
err = -EBUSY;
goto abort;
}
* any io in the removed space completes, but it hardly seems
* worth it.
*/
- raid5_conf_t *conf = mddev_to_conf(mddev);
-
sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
- mddev->array_sectors = sectors * (mddev->raid_disks
- - conf->max_degraded);
+ md_set_array_sectors(mddev, raid5_size(mddev, sectors,
+ mddev->raid_disks));
+ if (mddev->array_sectors >
+ raid5_size(mddev, sectors, mddev->raid_disks))
+ return -EINVAL;
set_capacity(mddev->gendisk, mddev->array_sectors);
mddev->changed = 1;
if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) {
return 0;
}
-#ifdef CONFIG_MD_RAID5_RESHAPE
static int raid5_check_reshape(mddev_t *mddev)
{
raid5_conf_t *conf = mddev_to_conf(mddev);
- int err;
- if (mddev->delta_disks < 0 ||
- mddev->new_level != mddev->level)
- return -EINVAL; /* Cannot shrink array or change level yet */
- if (mddev->delta_disks == 0)
- return 0; /* nothing to do */
+ if (mddev->delta_disks == 0 &&
+ mddev->new_layout == mddev->layout &&
+ mddev->new_chunk == mddev->chunk_size)
+ return -EINVAL; /* nothing to do */
if (mddev->bitmap)
/* Cannot grow a bitmap yet */
return -EBUSY;
+ if (mddev->degraded > conf->max_degraded)
+ return -EINVAL;
+ if (mddev->delta_disks < 0) {
+ /* We might be able to shrink, but the devices must
+ * be made bigger first.
+ * For raid6, 4 is the minimum size.
+ * Otherwise 2 is the minimum
+ */
+ int min = 2;
+ if (mddev->level == 6)
+ min = 4;
+ if (mddev->raid_disks + mddev->delta_disks < min)
+ return -EINVAL;
+ }
/* Can only proceed if there are plenty of stripe_heads.
* We need a minimum of one full stripe,, and for sensible progress
if ((mddev->chunk_size / STRIPE_SIZE) * 4 > conf->max_nr_stripes ||
(mddev->new_chunk / STRIPE_SIZE) * 4 > conf->max_nr_stripes) {
printk(KERN_WARNING "raid5: reshape: not enough stripes. Needed %lu\n",
- (mddev->chunk_size / STRIPE_SIZE)*4);
+ (max(mddev->chunk_size, mddev->new_chunk)
+ / STRIPE_SIZE)*4);
return -ENOSPC;
}
- err = resize_stripes(conf, conf->raid_disks + mddev->delta_disks);
- if (err)
- return err;
-
- if (mddev->degraded > conf->max_degraded)
- return -EINVAL;
- /* looks like we might be able to manage this */
- return 0;
+ return resize_stripes(conf, conf->raid_disks + mddev->delta_disks);
}
static int raid5_start_reshape(mddev_t *mddev)
*/
return -EINVAL;
+ /* Refuse to reduce size of the array. Any reductions in
+ * array size must be through explicit setting of array_size
+ * attribute.
+ */
+ if (raid5_size(mddev, 0, conf->raid_disks + mddev->delta_disks)
+ < mddev->array_sectors) {
+ printk(KERN_ERR "md: %s: array size must be reduced "
+ "before number of disks\n", mdname(mddev));
+ return -EINVAL;
+ }
+
atomic_set(&conf->reshape_stripes, 0);
spin_lock_irq(&conf->device_lock);
conf->previous_raid_disks = conf->raid_disks;
conf->raid_disks += mddev->delta_disks;
- conf->expand_progress = 0;
- conf->expand_lo = 0;
+ conf->prev_chunk = conf->chunk_size;
+ conf->chunk_size = mddev->new_chunk;
+ conf->prev_algo = conf->algorithm;
+ conf->algorithm = mddev->new_layout;
+ if (mddev->delta_disks < 0)
+ conf->reshape_progress = raid5_size(mddev, 0, 0);
+ else
+ conf->reshape_progress = 0;
+ conf->reshape_safe = conf->reshape_progress;
+ conf->generation++;
spin_unlock_irq(&conf->device_lock);
/* Add some new drives, as many as will fit.
break;
}
- spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = (conf->raid_disks - conf->previous_raid_disks) - added_devices;
- spin_unlock_irqrestore(&conf->device_lock, flags);
+ if (mddev->delta_disks > 0) {
+ spin_lock_irqsave(&conf->device_lock, flags);
+ mddev->degraded = (conf->raid_disks - conf->previous_raid_disks)
+ - added_devices;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ }
mddev->raid_disks = conf->raid_disks;
mddev->reshape_position = 0;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
mddev->recovery = 0;
spin_lock_irq(&conf->device_lock);
mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
- conf->expand_progress = MaxSector;
+ conf->reshape_progress = MaxSector;
spin_unlock_irq(&conf->device_lock);
return -EAGAIN;
}
+ conf->reshape_checkpoint = jiffies;
md_wakeup_thread(mddev->sync_thread);
md_new_event(mddev);
return 0;
}
-#endif
+/* This is called from the reshape thread and should make any
+ * changes needed in 'conf'
+ */
static void end_reshape(raid5_conf_t *conf)
{
- struct block_device *bdev;
if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
- conf->mddev->array_sectors = conf->mddev->dev_sectors *
- (conf->raid_disks - conf->max_degraded);
- set_capacity(conf->mddev->gendisk, conf->mddev->array_sectors);
- conf->mddev->changed = 1;
-
- bdev = bdget_disk(conf->mddev->gendisk, 0);
- if (bdev) {
- mutex_lock(&bdev->bd_inode->i_mutex);
- i_size_write(bdev->bd_inode,
- (loff_t)conf->mddev->array_sectors << 9);
- mutex_unlock(&bdev->bd_inode->i_mutex);
- bdput(bdev);
- }
+
spin_lock_irq(&conf->device_lock);
- conf->expand_progress = MaxSector;
+ conf->previous_raid_disks = conf->raid_disks;
+ conf->reshape_progress = MaxSector;
spin_unlock_irq(&conf->device_lock);
- conf->mddev->reshape_position = MaxSector;
+ wake_up(&conf->wait_for_overlap);
/* read-ahead size must cover two whole stripes, which is
* 2 * (datadisks) * chunksize where 'n' is the number of raid devices
*/
{
- int data_disks = conf->previous_raid_disks - conf->max_degraded;
- int stripe = data_disks *
- (conf->mddev->chunk_size / PAGE_SIZE);
+ int data_disks = conf->raid_disks - conf->max_degraded;
+ int stripe = data_disks * (conf->chunk_size
+ / PAGE_SIZE);
if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
}
}
}
+/* This is called from the raid5d thread with mddev_lock held.
+ * It makes config changes to the device.
+ */
+static void raid5_finish_reshape(mddev_t *mddev)
+{
+ struct block_device *bdev;
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+
+ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+
+ if (mddev->delta_disks > 0) {
+ md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
+ set_capacity(mddev->gendisk, mddev->array_sectors);
+ mddev->changed = 1;
+
+ bdev = bdget_disk(mddev->gendisk, 0);
+ if (bdev) {
+ mutex_lock(&bdev->bd_inode->i_mutex);
+ i_size_write(bdev->bd_inode,
+ (loff_t)mddev->array_sectors << 9);
+ mutex_unlock(&bdev->bd_inode->i_mutex);
+ bdput(bdev);
+ }
+ } else {
+ int d;
+ mddev->degraded = conf->raid_disks;
+ for (d = 0; d < conf->raid_disks ; d++)
+ if (conf->disks[d].rdev &&
+ test_bit(In_sync,
+ &conf->disks[d].rdev->flags))
+ mddev->degraded--;
+ for (d = conf->raid_disks ;
+ d < conf->raid_disks - mddev->delta_disks;
+ d++)
+ raid5_remove_disk(mddev, d);
+ }
+ mddev->layout = conf->algorithm;
+ mddev->chunk_size = conf->chunk_size;
+ mddev->reshape_position = MaxSector;
+ mddev->delta_disks = 0;
+ }
+}
+
static void raid5_quiesce(mddev_t *mddev, int state)
{
raid5_conf_t *conf = mddev_to_conf(mddev);
return setup_conf(mddev);
}
+static void *raid5_takeover_raid6(mddev_t *mddev)
+{
+ int new_layout;
+
+ switch (mddev->layout) {
+ case ALGORITHM_LEFT_ASYMMETRIC_6:
+ new_layout = ALGORITHM_LEFT_ASYMMETRIC;
+ break;
+ case ALGORITHM_RIGHT_ASYMMETRIC_6:
+ new_layout = ALGORITHM_RIGHT_ASYMMETRIC;
+ break;
+ case ALGORITHM_LEFT_SYMMETRIC_6:
+ new_layout = ALGORITHM_LEFT_SYMMETRIC;
+ break;
+ case ALGORITHM_RIGHT_SYMMETRIC_6:
+ new_layout = ALGORITHM_RIGHT_SYMMETRIC;
+ break;
+ case ALGORITHM_PARITY_0_6:
+ new_layout = ALGORITHM_PARITY_0;
+ break;
+ case ALGORITHM_PARITY_N:
+ new_layout = ALGORITHM_PARITY_N;
+ break;
+ default:
+ return ERR_PTR(-EINVAL);
+ }
+ mddev->new_level = 5;
+ mddev->new_layout = new_layout;
+ mddev->delta_disks = -1;
+ mddev->raid_disks -= 1;
+ return setup_conf(mddev);
+}
+
static int raid5_reconfig(mddev_t *mddev, int new_layout, int new_chunk)
{
- /* Currently the layout and chunk size can only be changed
- * for a 2-drive raid array, as in that case no data shuffling
- * is required.
- * Later we might validate these and set new_* so a reshape
- * can complete the change.
+ /* For a 2-drive array, the layout and chunk size can be changed
+ * immediately as not restriping is needed.
+ * For larger arrays we record the new value - after validation
+ * to be used by a reshape pass.
*/
raid5_conf_t *conf = mddev_to_conf(mddev);
/* They look valid */
- if (mddev->raid_disks != 2)
- return -EINVAL;
+ if (mddev->raid_disks == 2) {
- if (new_layout >= 0) {
- conf->algorithm = new_layout;
- mddev->layout = mddev->new_layout = new_layout;
+ if (new_layout >= 0) {
+ conf->algorithm = new_layout;
+ mddev->layout = mddev->new_layout = new_layout;
+ }
+ if (new_chunk > 0) {
+ conf->chunk_size = new_chunk;
+ mddev->chunk_size = mddev->new_chunk = new_chunk;
+ }
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ md_wakeup_thread(mddev->thread);
+ } else {
+ if (new_layout >= 0)
+ mddev->new_layout = new_layout;
+ if (new_chunk > 0)
+ mddev->new_chunk = new_chunk;
}
+ return 0;
+}
+
+static int raid6_reconfig(mddev_t *mddev, int new_layout, int new_chunk)
+{
+ if (new_layout >= 0 && !algorithm_valid_raid6(new_layout))
+ return -EINVAL;
if (new_chunk > 0) {
- conf->chunk_size = new_chunk;
- mddev->chunk_size = mddev->new_chunk = new_chunk;
+ if (new_chunk & (new_chunk-1))
+ /* not a power of 2 */
+ return -EINVAL;
+ if (new_chunk < PAGE_SIZE)
+ return -EINVAL;
+ if (mddev->array_sectors & ((new_chunk>>9)-1))
+ /* not factor of array size */
+ return -EINVAL;
}
- set_bit(MD_CHANGE_DEVS, &mddev->flags);
- md_wakeup_thread(mddev->thread);
+
+ /* They look valid */
+
+ if (new_layout >= 0)
+ mddev->new_layout = new_layout;
+ if (new_chunk > 0)
+ mddev->new_chunk = new_chunk;
+
return 0;
}
if (mddev->level == 1)
return raid5_takeover_raid1(mddev);
+ if (mddev->level == 4) {
+ mddev->new_layout = ALGORITHM_PARITY_N;
+ mddev->new_level = 5;
+ return setup_conf(mddev);
+ }
+ if (mddev->level == 6)
+ return raid5_takeover_raid6(mddev);
return ERR_PTR(-EINVAL);
}
.spare_active = raid5_spare_active,
.sync_request = sync_request,
.resize = raid5_resize,
-#ifdef CONFIG_MD_RAID5_RESHAPE
+ .size = raid5_size,
.check_reshape = raid5_check_reshape,
.start_reshape = raid5_start_reshape,
-#endif
+ .finish_reshape = raid5_finish_reshape,
.quiesce = raid5_quiesce,
.takeover = raid6_takeover,
+ .reconfig = raid6_reconfig,
};
static struct mdk_personality raid5_personality =
{
.spare_active = raid5_spare_active,
.sync_request = sync_request,
.resize = raid5_resize,
-#ifdef CONFIG_MD_RAID5_RESHAPE
+ .size = raid5_size,
.check_reshape = raid5_check_reshape,
.start_reshape = raid5_start_reshape,
-#endif
+ .finish_reshape = raid5_finish_reshape,
.quiesce = raid5_quiesce,
.takeover = raid5_takeover,
.reconfig = raid5_reconfig,
.spare_active = raid5_spare_active,
.sync_request = sync_request,
.resize = raid5_resize,
-#ifdef CONFIG_MD_RAID5_RESHAPE
+ .size = raid5_size,
.check_reshape = raid5_check_reshape,
.start_reshape = raid5_start_reshape,
-#endif
+ .finish_reshape = raid5_finish_reshape,
.quiesce = raid5_quiesce,
};
static int __init raid5_init(void)
{
- int e;
-
- e = raid6_select_algo();
- if ( e )
- return e;
register_md_personality(&raid6_personality);
register_md_personality(&raid5_personality);
register_md_personality(&raid4_personality);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff